To avoid the scalability of the existing systems that employed centralized indexing, index flooding or query flooding, we proposed an efficient peer-to-peer information retrieval system SPIRS (Semantic P2P-based Information Retrieval System) that supported state-of-the-art content and semantic searches. SPIRS distributes document indices through P2P network hierarchically by Latent Semantic Indexing (LSI) and organizes nodes into a hierarchical overlay through CAN and TRIE. Comparing with other P2P search techniques, those based on simple keyword matching, SPIRS has better accuracy for considering the advanced relevance among documents. Given a query, only a small number of nodes are needed for SPIRS to identify the matching documents.Furthermore, both theoretical analysis and experimental results show that SPIRS possesses higher accuracy and less logic hops.