slow xsltproc XInclude processing w/complex document?

I've been running some tests on a document that includes nested
Xinclude directives. The document is complex: upwards of 1500 files,
nested to a depth of up to 4 levels.  Total size of content is about 4.8MB.

For simple testing, I'm attempting only to produce a "flattened"
document that just resolves the XIincludes.  Stylesheet looks like
this:

<?xml version="1.0" encoding="UTF-8"?>
<xsl:stylesheet version="1.0" xmlns:xsl="http://www.w3.org/1999/XSL/Transform">

<xsl:output method="xml" indent="yes"/>
<xsl:preserve-space elements="*"/>

<xsl:template match="xi:include" xmlns:xi="http://www.w3.org/2001/XInclude">
  <xsl:for-each select="document(@href)">
    <xsl:apply-templates/>
  </xsl:for-each>
</xsl:template>

<xsl:template match="/ | node() | @* | comment() | processing-instruction()">
  <xsl:copy>
    <xsl:apply-templates select="@* | node()"/>
  </xsl:copy>
</xsl:template>

This takes about 12 minutes on my 900 MHz G3 iBook (Mac OS X), and about
4 minutes on my 2.8 GHz Pentium 4 Gentoo Linux box.

That seems pretty slow, particular given that the control condition takes
mere seconds (running the flattenedly document through a standard identity
transform with xsltproc).

I don't want to post the input here because it's so big, so this is really
just a preliminary post to ask for advice as to how I might go about
improving the XInclude-d transform: Is this a known issue with
xsltproc/XInclude?  Or is there perhaps some flag I should be using that I
am failing to use?  Something bad about my stylesheet?