This paper describes our participation in the opinion retrieval task at Blog Track 07. The system consisted of the preprocess part, the topic retrieval part and sentiment analysis part. In the topic retrieval part, we adopted pseudo-relevance feedback and a novel approach to form a modified query. In the sentiment analysis part, each blog post was given an opinion score based on the sentences contained in this post. The subjectivity of each sentence was predicted by a CME classifier. Then the blog posts were reranked based on the similarity given by the topic retrieval and the opinion score given by the sentiment analysis.