Post-transcriptional regulation, though less studied, is an important research topic in bioinformatics. In a set of post-transcriptionally coregulated RNAs, the basepair interactions can organize the molecules into domains and provide a framework for functional interactions. Their consensus motifs may represent the binding sites of RNA regulatory proteins. Unlike DNA motifs, RNA motifs are more conserved in structures than in sequences. Knowing the structural motifs can help us better understand the regulation activities. In this paper, we propose a novel data mining approach to RNA secondary structure prediction. To demonstrate the performance of our new approach, we first tested it on the same data sets previously used and published in literature. Secondly, to show the flexibility of our new approach, we also tested it on a data set that contains pseudoknot motifs that most current systems cannot identify.