I'm curious why you chose to use an expensive wildcard string pattern match instead of using XQuery with the XML Namespace to query this information? An example of how you can parse the XML Doc using the DOM can be found on the following blog post:
Digging into the SQL Plan Cache: Finding Missing Indexes
Jonathan Kehayias | Principal Consultant | MCM: SQL Server 2008
My Blog | Twitter | MVP Profile
Training | Consulting | Become a SQLskills Insider
Troubleshooting SQL Server: A Guide for Accidental DBAs[/url]