This paper presents a distributed multi-robot system to search for odor sources inside unknown environments. The robots cooperatively explore the whole environment and generate its topological map. The exploration method is a decentralized frontier based algorithm that is enhanced by considering odor concentration at each frontier inside its cost/gain function. The robots independently generate local topological maps and by transferring them to each other, they are able to integrate these maps and generate a whole global map. The proposed method was tested and validated in real reduced scale scenarios.