For the last few years peer-to-peer (p2p) networks have become widely used tools for sharing any kind of information from multimedia data to text documents. The vast amount of shared information leads issues on finding relevant information over p2p networks. Existing p2p file search and information retrieval techniques are based on the name of files, which is insufficient when searching relevant documents. In this paper we present a method to perform semantic information retrieval over p2p networks. Our method semantically inspects the content of shared data in peers to generate conceptual information about documents and general information about the peer.