It would appear that the DOM Tree generated by the SimpleHtmlParser does not (for some reason I haven't been able to figure out) support any XPath functionality other than "//*".
I have a simple XHTML document that I load via SimpleHtmlParser's Parse method. I can walk the DOM Tree just fine but if I use SelectNodes() with anything but "//*" I end up with 0 results.
Loading the XHTML directly using XmlDocument's Load functionality results in a DOM that returns expected results for any given XPath query.