In this paper we propose a novel algorithm called Rank-Based Broadcast (RBB) for discovery of local resources in mobile P2P networks. With RBB, each moving object periodically broadcasts the most relevant resource reports and queries it knows to its neighbors, and the contribution is in determining how to rank the reports and queries in terms of their relevance, when to broadcast them, and how many to broadcast. A major difference between RBB and many existing algorithms in the resource discovery and publish/subscribe literature is that RBB does not rely on any pre-established routing structure, and therefore is able to adapt to both high mobility environments. In the paper we experimentally compare RBB with flooding and PSTree, a publish/subscribe algorithm for wireless ad-hoc networks. The results show that RBB by far outperforms the other two algorithms.