Large-scale sensor networks (LSSN's) are formed when very large numbers of miniaturized sensor nodes with wireless communication capability are deployed randomly over an extended region, e.g., scattered from the air or embedded in material. Systems such as smart matter, smart paint and smart dust imply the existence of LSSN's, but they can also be used in applications involving large geographical regions such as environmental monitoring or disaster relief. Our contention is that, given their scale and random structure, LSSN's should be treated as complex systems rather than as standard wireless networks. Approaches from wireless networks typically have difficulty scaling up to large numbers of nodes, especially when the nodes have limited capabilities and are deployed over a region much larger than their communication range. We explore how a system comprising of very large number of randomly distributed sensor nodes can organize itself to communicate information. To keep the system realistic, we assume that nodes in our system are unreliable, have limited energy resources and have minimal on-board computational capabilities. Our focus is on the efficient routing of messages in such a system, specifically on the network algorithms aspect, rather than on issues such as hardware, signal processing and communication. The goal is to develop a system that scales effectively and is robust to node failures. The approach we propose is to limit the usage of bandwidth and energy while tapping the inherent parallelism of simple flooding to achieve robustness. Simulation results show significant improvement in performance compared to simple flooding algorithms.